shrinkt.st: Calculate 'Shrinkage t' Statistic

In tileHMM: Hidden Markov Models for ChIP-on-Chip Analysis

Description

Calculate the ‘shrinkage t’ statistic (Opgen-Rhein and Strimmer, 2007).

Usage

shrinkt.st(X, L, h0.mean = 0, ...)

Arguments

X	Data matrix. Rows correspond to variables (probes) and columns to samples.
L	Design vector. Indicating treatment (1) and control (2) samples. If no control samples are given a one sample t test is carried out.
h0.mean	If no control samples are provided the treatment mean is compared to this value in a one sample t test.
...	Further arguments to be passed to and from other methods.

Value

An object of class "shrinkage" containing the test statistics.

Note

This method uses the shrinkt.stat method from package st.

Author(s)

Peter Humburg

References

Opgen-Rhein, R., and K. Strimmer 2007. Accurate ranking of differentially expressed genes by a distribution-free shrinkage approach. Statist. Appl. Genet. Mol. Biol. 6:9. http://www.bepress.com/sagmb/vol6/iss1/art9/

See Also

shrinkt.stat

Examples

## generate some data
X <- matrix(nrow = 100, ncol = 6)
X[ , 1:3] <- apply(X[ , 1:3], 1, rnorm, 
    mean = rnorm(1, mean = 2, sd = 2), sd = rchisq(1, df = 2))
X[ , 4:6] <- apply(X[ , 4:6], 1, rnorm, 
    mean = rnorm(1, mean = 0, sd = 1), sd = rchisq(1, df = 2))
L <- c(1, 1, 1, 2, 2, 2)

## compute shrinkage t statistic
st.stat <- shrinkt.st(X, L)

tileHMM documentation built on May 30, 2017, 3:41 a.m.